README.md

metadata

base_model:
  - openchat/openchat-3.5-1210
  - beowolx/CodeNinja-1.0-OpenChat-7B
license: mit
tags:
  - moe
  - frankenmoe
  - merge
  - mergekit
  - openchat/openchat-3.5-1210
  - beowolx/CodeNinja-1.0-OpenChat-7B

prueba-moe

prueba-moe is a Mixture of Experts (MoE) made with the following models using Mergekit:

• openchat/openchat-3.5-1210
• beowolx/CodeNinja-1.0-OpenChat-7B

🧩 Configuration

experts:
- positive_prompts:
  - chat
  - assistant
  - tell me
  - explain
  - what is
  source_model: openchat/openchat-3.5-1210
- positive_prompts:
  - code
  - python
  - javascript
  - programming
  - algorithm
  source_model: beowolx/CodeNinja-1.0-OpenChat-7B
experts_per_token: 2
gate_mode: cheap_embed

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mgv99/prueba-moe"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])